Independent directorynot affiliated with xAI
Catalog refreshed Nobody pays to be listed or ranked
9,075 templates from 4,179 creators, each showing what it connects to, whether it asks first and how often it runs. “Checked” means the link was reachable — not a safety rating.
Watches OpenAI Codex, Claude, Gemini, Cursor, Grok, and other AI products for new versions; say "look" and it checks the official sources and tells you what's new. For anyone who wan…
A dependency security watch for your GitHub repos. Twice a day it checks OSV, CISA KEV, Cloudflare Zero Wire, and security mailing lists against your…
Assumes your work is a 3/10, then shows exactly what gets it to a 7 and a 10. Scores writing, code, designs or plans on the dimensions you pick, runs a second critic pass on its own…
Audita tus repos de GitHub cada semana, solo lectura: secretos filtrados (incluido el historial), dependencias vulnerables, alertas, protección de ramas y workflows, con riesgo y opc…
Builds phone workout apps where each lift keeps a YouTube form demo with a saved start time, so Watch demo jumps straight to the cue. For anyone who…
Reads your X bookmarks every day and tips off the one teammate bot best placed to use each item, with the link and a one-line why. Read only, quiet when there is nothing new.
Sends a short weekday summary of how much of your monthly Claude API credit is left in your Claude Console organization, calculated read-only from the Admin API cost report.
A coding bot that runs the Claude Code CLI on its own computer, signed in with your Claude plan or API key and your GitHub, and never pushes or merges without your approval.
Reads every new commit to X's open-source algorithm repo, explains it in plain English, checks viral 'algorithm hack' claims against the actual code, and turns real changes into post…
Runs deep, evidence-based security, malware, supply-chain, and code-quality audits of GitHub repositories you're authorized to assess, and can prepare fixes on a review branch. Repor…
Each morning it walks GitHub's trending page and keeps only the projects touching the languages and tools you actually work in. What arrives is a short read: a line or two per reposi…
Puts your bot's cloud box on your tailnet safely, then audits ACLs, manages devices, sets up Tailscale SSH, and troubleshoots, confirming before every change. For Tailscale users who…
A conversational bridge between you and your coding agent (Claude Code, Codex, Cursor and others). It carries your requests, brings back answers, does the web research for it and tel…
Say "check my bots" and it reviews your other bots' chat histories, then tells you which ones should be reset with a fresh copy now, soon, or not yet. For bots that need a reset, it…
A poteto-mode engineering partner. It goes deep before going broad, ships the least code that works, proves results on the real artifact, and hands coding off to cloud agents with a…
Email authentication is its entire remit. Hand it your DMARC report data and it tells a genuine authentication problem apart from the routine noise gateways generate. From there it c…
A Spanish-language coordinator for a Grok team of specialists. Work is assigned so nobody strays into a teammate's area, one vault is kept for the whole team to read from, and the we…
Keeps a read-only eye on your Ubiquiti UniFi networks and sends a daily health report with offline devices, WAN status, and speed test results.
Software-shipping mother bot. You give one long problem plus a done definition; it orchestrates specialist seats in parallel, never does the specialist work itself, and wakes you onl…
Quality-checks GeoJSON, Shapefile, GeoPackage and KML files and WMS/WFS/OGC API services: geometry validity, CRS and axis order, extent, attributes, polygon overlaps and gaps, size a…
Guards your data with DataContractGate: drafts a contract from a sample file, validates files and feeds against it, explains quarantined records in plain words, and sends a digest on…
A careful lead software engineer for your website. Builds approved changes through cloud agents and draft PRs, tests and secret-scans every push, and never merges or deploys without…
An honest, read-only evaluator that tells you whether a repo, connector, plugin, skill, CLI, app, or extension is worth installing, how safe it is, and how to install it with the lea…
It sweeps your GitHub notifications, open PRs and CI runs, then returns a short list of items that genuinely need a person, each with one concrete next step. Anything consequential,…
A rigor reviewer for agentic engineering, built on the pstack method. It checks plans and specs, demands re-runnable proof, and makes sure no agent signs off its own work, with deter…
A senior QA and test-automation lead for testers and dev teams. It turns requirements into test plans, triages flaky tests, reviews Playwright, Selenium and Appium code, writes bug r…
Runs T3 Code from chat on your own computers (macOS, Linux or Windows) through the `t3` CLI: it starts, messages and checks on coding-agent threads (Codex, Claude Code, and more), ha…
Designs Hot Wheels–scale play mats of real places: accurate wireframes, azimuth guides, modular road/rail/river SVG parts, scavenger wildlife, and a path to print-on-demand art. For…
Hands your heavy jobs (code, apps, long research, big documents, long-form writing, data work, reviews) to Claude Code or Codex using your own subscription, and handles quick work it…
List your devices once. I flag exploited bugs that hit them, rank what to update today, with steps and links. I check CISA's Known Exploited Vulnerabilities catalog and official vend…
A tools admin for your bot computer. Installs and updates developer tools, keeps the browser and memory use tidy, and checks that sign-ins stay healthy. Asks before any install or re…
Sets up a free, read-only file indexer on your Windows PC so your bots can search your files by name, content, type and date in seconds.
Adversarial review of code, plans, and review pipelines, with the independent reviewer running on your own Hermes agent (a different model). Findings come back proven, ranked, and ei…
Runs day-to-day releases for a portfolio of mobile and web apps: store builds, TestFlight and Play testing, App Store review and rejection fixes, and listing assets. It stops for you…
Paste a pull request and get the reviewer's brief in under 2 minutes: what changed vs the ticket, risky spots with file and line, what to test by hand, and questions for the author.…
Each morning this bot works through what is climbing GitHub's trending list and picks out a small number of projects to write up in Chinese, with a plain summary of the problem each…